caliex commited on
Commit
b9cec0f
1 Parent(s): c2594e8

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -2
app.py CHANGED
@@ -47,7 +47,8 @@ parameters = [
47
  gr.inputs.Slider(10, 100, step=10, default=50, label="Number of data points (n)"),
48
  gr.inputs.Slider(-50, 50, step=1, default=-50, label="Random Value Range (Min)"),
49
  gr.inputs.Slider(-50, 50, step=1, default=50, label="Random Value Range (Max)"),
50
- gr.inputs.Dropdown(["clip", "nan", "raise"], default="clip", label="Out of Bounds Strategy"),
 
51
  ]
52
 
53
  description = "This app presents an illustration of the isotonic regression on generated data (non-linear monotonic trend with homoscedastic uniform noise). The isotonic regression algorithm finds a non-decreasing approximation of a function while minimizing the mean squared error on the training data. The benefit of such a non-parametric model is that it does not assume any shape for the target function besides monotonicity. For comparison a linear regression is also presented. See the original scikit-learn example here: https://scikit-learn.org/stable/auto_examples/miscellaneous/plot_isotonic_regression.html"
@@ -58,5 +59,5 @@ examples = [
58
  [70, -10, 20, "raise"],
59
  ]
60
 
61
- iface = gr.Interface(fn=visualize_isotonic_regression, inputs=parameters, outputs="plot", title="Isotonic Regression Visualization", description=description, examples=examples)
62
  iface.launch()
 
47
  gr.inputs.Slider(10, 100, step=10, default=50, label="Number of data points (n)"),
48
  gr.inputs.Slider(-50, 50, step=1, default=-50, label="Random Value Range (Min)"),
49
  gr.inputs.Slider(-50, 50, step=1, default=50, label="Random Value Range (Max)"),
50
+ gr.inputs.Radio(["clip", "nan", "raise"], default="clip", label="Out of Bounds Strategy"),
51
+ # gr.inputs.Dropdown(["clip", "nan", "raise"], default="clip", label="Out of Bounds Strategy"),
52
  ]
53
 
54
  description = "This app presents an illustration of the isotonic regression on generated data (non-linear monotonic trend with homoscedastic uniform noise). The isotonic regression algorithm finds a non-decreasing approximation of a function while minimizing the mean squared error on the training data. The benefit of such a non-parametric model is that it does not assume any shape for the target function besides monotonicity. For comparison a linear regression is also presented. See the original scikit-learn example here: https://scikit-learn.org/stable/auto_examples/miscellaneous/plot_isotonic_regression.html"
 
59
  [70, -10, 20, "raise"],
60
  ]
61
 
62
+ iface = gr.Interface(fn=visualize_isotonic_regression, inputs=parameters, outputs="plot", title="Isotonic Regression Visualization", description=description, examples=examples, live=True)
63
  iface.launch()